Journal Article

A recurrent neural network for variable admittance control in human–robot cooperation: simultaneously and online adjustment of the virtual damping and Inertia parameters

Sharkawy, Abdel-Nasser, Aspragathos, Nikos, Koustoumpardis, Panagiotis N.

2020

Overview

In this manuscript, a recurrent neural network is proposed for variable admittance control in human–robot cooperation tasks. The virtual damping and the virtual inertia of the designed robot’s admittance controller are adjusted online and simultaneously. A Jordan recurrent neural network is designed and trained for this purpose. The network is indirectly trained using the real-time recurrent learning algorithm and based on the velocity error between the reference velocity of the minimum jerk trajectory model and the actual velocity of the robot. The performance of the proposed variable admittance controller is presented in terms of the human required effort, the task completion time, the achieved accuracy at the target, and the oscillations during the movement. Its generalization ability is evaluated experimentally by conducting cooperative tasks along numerous straight-line segments using the KUKA LWR robot and by ten subjects. Finally, a comparison with previous developed variable admittance controllers, where only the variable damping or only the virtual inertia is adjusted, is presented.

• Publisher: Springer Singapore,Springer Nature B.V
• Subject: Adaptation / Algorithms / Artificial Intelligence / Back propagation / Completion time / Computer Science / Control / Controllers / Cooperation / Damping / Electrical impedance / Electronics and Microelectronics / Fourier transforms / Inertia / Instrumentation / Machine learning / Machines / Manufacturing / Mechatronics / Neural networks / Processes / Recurrent neural networks / Regular Paper / Robot control / Robotics / Robots / Sensors / User Interfaces and Human Computer Interaction / Velocity / Velocity errors